domino logo
Latest (5.4)
  • Tech Ecosystem
  • Deployment-wide Search
  • Get Started
  • Security and Credentials
  • Collaborate
  • Organizations
  • Projects
  • Domino Datasets
  • External Data
  • Workspaces
  • Environments
  • Executions
  • Model APIs
  • Publish
  • Model Monitoring and Remediation
  • Notifications
  • Download the Audit Log
  • Domino Command Line Interface (CLI)
  • Troubleshooting
  • Get Help
domino logo
About Domino
Domino Data LabKnowledge BaseData Science BlogTraining
User Guide
>
Publish
>
Externally-Hosted Models
>
Model Requirements

Model Requirements

The model that you create in Domino must meet the following requirements to be hosted in Snowflake:

  • Model must be created in Python 3.8.

  • You must create a file named requirements.txt in the root folders (for example, the root folder of the main Git-based project, root folder of an imported repository, or root folder of imported projects)

    This file defines the list of required packages for the model. See https://github.com/binder-examples/requirements/blob/master/requirements.txt for an example, and see Add Packages to Environments for more details.

    • These packages must be in the Snowflake Anaconda list: https://repo.anaconda.com/pkgs/snowflake/.

    • If you use external packages, your Snowflake instance must enable usage of Anaconda packages.

  • Must have Python-type hints for the model function input and return variables.

For the model to be monitored, you must have the following:

  • A timestamp column in your prediction dataset.

  • The name of the table that contains the prediction data.

Domino looks for entries in table with new timestamps to continuously ingest new data in batches.

Domino Data LabKnowledge BaseData Science BlogTraining
Copyright © 2022 Domino Data Lab. All rights reserved.